© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 19311
    Prev
    Next
    INDEX
    Explanations

    words related to actions or interactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of actions and movements described in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovi
    -0.71
    irable
    -0.65
    hare
    -0.64
    senal
    -0.59
    represented
    -0.59
     occupant
    -0.58
     Mali
    -0.58
    uded
    -0.58
     Mold
    -0.57
     Contributions
    -0.57
    POSITIVE LOGITS
     cautiously
    0.99
    yss
    0.90
     reluctantly
    0.84
     nervously
    0.84
     instinctively
    0.80
     aback
    0.75
    agall
    0.75
     realise
    0.74
     wondering
    0.73
     quizz
    0.73
    Activations Density 0.307%

    No Known Activations